Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mlflow/ui-review
Review a GitHub PR's UI/UX changes by launching the MLflow web app, driving a headless agent-browser over the changed surfaces, and writing a Markdown UI-review comment body (findings + screenshots) for the workflow to post.
Passed 13 of 20 test cases with the skill, and 8 of 20 without it.
and 6 more in the full report
8 fixed8 passed either way7 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Before executing browser interactions with agent-browser, what command ensures the latest authoritative agent-browser reference is loaded?
| Checked | Without skill | With skill |
|---|---|---|
| Runs agent-browser skills get core --full prior to browser operations | Missed | Passed |
The instructions your model reads when the skill loads.
You review the rendered UI/UX of a PR's frontend changes by driving a real (headless)
browser against a locally-running MLflow app — the visual counterpart to the pr-review
code-review skill. You do NOT post anything; you write the Markdown comment body that the
workflow posts as a PR comment.
/ui-review <owner_repo> <pr_number> <app_url>
<owner_repo> (required): repository slug, e.g. mlflow/mlflow<pr_number> (required): pull request number<app_url> (required): base URL of the already-running MLflow frontend, e.g. http://localhost:3000Split $owner_repo on / for <owner> and <repo>. The PR URL is
https://github.com/<owner>/<repo>/pull/<pr_number>.
These reads are independent. Issue them as parallel tool calls in a single turn.
gh pr view <pr_number> --repo <owner>/<repo> --json title,body,filesgit diff HEAD^1 HEAD | uv run --package skills skills annotate-diff --files 'mlflow/server/js/src/**'refs/pull/<pr>/merge):
git diff --name-only HEAD^1 | grep '^mlflow/server/js/src/'reviewThreads, filtering to UI-relevant paths).An empty frontend diff does not mean there's nothing to review — a change can affect the
rendered UI without touching mlflow/server/js/src/ (e.g. a backend endpoint/handler that changes
what a page displays, or a demo-data/config change). Decide from the whole picture — the changed
test cases passed, vs 8 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.